🎯 Research Hypothesis
Loading hypothesis...
Definitions
Verdict

The report verdict is written by the LLM in Stage 4 by combining Lyra’s data graph outputs with domain knowledge and (optionally) external tools. The dashboard displays the verdict from report_summary.json as the single source of truth.

Links

A “link” is a relationship extracted into the data graph (e.g., fragment→claim edges and other provenance relationships). Timeline values represent the number of fragment→claim links per year for the selected task.

Claims

Atomic factual statements extracted from literature by LLM. Each claim represents a single verifiable assertion about the research hypothesis. Claims are the fundamental unit of evidence analysis.

Contradictions

Claims with ≥1 "refutes" evidence edge from NLI classification. Indicates areas of scientific disagreement.
Controversy Score = refute_count / (support_count + refute_count + 1). Range: 0–1.

NLI Claim Support Ratio

An exploration score derived from fragment→claim NLI evidence edges (supports vs refutes weights).
0.50 means “no net tilt (or insufficient/offsetting evidence)”, not “50% efficacy”.

Key Source Score

In this dashboard, the source score is the number of distinct claims supported by a page (count of fragment→claim edges with relation “supports/origin” for the task). Displayed in Key Supporting Sources.

Page / Fragment

A page is a fetched source document (URL) in the data graph. A fragment is an excerpt extracted from a page and linked to one or more claims. These are used to trace provenance.

📄 Exploration Reports

Loading reports...

🏆 Key Supporting Sources

Summary
Loading...

📈 Data Exploration Timeline

Summary
Loading...

🕸️ Data Provenance Network

All Years
2007201020132016201920222025All
DPP-4i Page
SGLT2i Page
Fragment
DPP-4i Claim
SGLT2i Claim
Cites (Page→Page)
Contains
Summary
Loading...